Skip to content

Run a set of experiments demonstrating the significance of "neural architectures as basis functions"  #7

Description

@nathanieljevans

See respective overleaf section.

Currently using different activation functions, however, better approach would be to use distinct architectures. Examples:

  • polynomial
  • NN
  • autoencoder
  • etc
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Metadata

Metadata

Assignees

No one assigned

    Labels

    enhancementNew feature or request

    Projects

    No projects

      Milestone

      No milestone

      Relationships

      None yet

      Development

      No branches or pull requests

      Issue actions